INDEX
Explanations
specific structured data or code snippets
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
263
+0.20
1.2%
307
+0.15
0.9%
342
+0.12
0.7%
Correlated Neurons
Index
P. Corr.
Cos Sim.
428
+0.20
0.15
298
+0.15
0.21
498
+0.12
0.19
Negative Logits
unnumbered
-1.59
ção
-1.58
ologia
-1.46
avian
-1.42
optic
-1.42
esium
-1.40
ocamp
-1.39
↵ ↵
-1.38
puted
-1.37
testified
-1.34
POSITIVE LOGITS
§
5.07
¼
4.92
½
4.90
Ĥ¬
4.79
ľĵ
4.79
ª
4.78
ĺ
4.74
Ĩ
4.71
¤
4.70
ĥ
4.68
Activations Density 6.971%